Enhancing robot evolution through Lamarckian principles
Jie Luo, Karine Miras, Jakub Tomczak, Agoston E. Eiben · 2023
Read Enhancing robot evolution through Lamarckian principles by Jie Luo, Karine Miras, Jakub Tomczak, Agoston E. Eiben (2023) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10689460.txt.
Description
Jie Luo, Karine Miras, Jakub Tomczak and Agoston Eiben test Lamarckian evolution in robots, in work from 2023. Their robots evolve both bodies and controllers, and they can also learn during their lifetimes. The study asks what happens if traits learned in life can be passed to offspring, as Lamarck proposed, rather than being lost as in a Darwinian setup.
Simulations compare a Lamarckian system with a Darwinian one on the same framework. Lamarckism boosted morphological intelligence, meaning a body's ability to gain a good brain through learning. Newborn robots did better because their inherited brains matched their bodies more closely. The work gives new insight into how evolution and learning interact.
Catalog record
| CREATOR | Jie Luo, Karine Miras, Jakub Tomczak, Agoston E. Eiben |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 79 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |